Performance of artificial neural network and regression techniques for rainfall-runoff prediction

A. El-Shafie, M. Mukhlisin, Ali A. Najah, Mohd. Raihan Taha

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

Different types of methods have been used in runoff prediction involving conceptual and empirical models. Nevertheless, none of these methods can be considered as a single superior model. Owing to the complexity of the hydrological process, the accurate runoff is difficult to be predicted using the linear recurrence relations or physically based watershed. The linear recurrence relation model does not attempt to take into account the nonlinear dynamic of the hydrological process. The Artificial Neural Network (ANN) is a new technique with a flexible mathematical structure that is capable of identifying complex non-linear relationships between input and output data when compared to other classical modelling techniques. Therefore, the present study aims to utilize an Artificial Neural Network (ANN) to predict the rainfall-runoff relationship in a catchment area located in a Tanakami region of Japan. The study illustrates the applications of the feed forward back propagation with hyperbolic tangent neurons in the hidden layer and linear neuron in the output layer is used for rainfall prediction. To evaluate the performance of the proposed model, three statistical indexes were used, namely; Correlation coefficient (R), mean square error (MSE) and correlation of determination (R2). The results showed that the feed forward back propagation Neural Network (ANN) can describe the behaviour of rainfall-runoff relation more accurately than the classical regression model.

Original languageEnglish
Pages (from-to)1997-2003
Number of pages7
JournalInternational Journal of Physical Sciences
Volume6
Issue number8
Publication statusPublished - Apr 2011

Fingerprint

drainage
Runoff
Rain
regression analysis
Neural networks
predictions
Backpropagation
neurons
Neurons
output
Watersheds
tangents
correlation coefficients
Mean square error
Catchments
Japan

Keywords

  • Artificial neural network
  • Linear regression
  • Rainfall-runoff

ASJC Scopus subject areas

  • Physics and Astronomy(all)
  • Electronic, Optical and Magnetic Materials

Cite this

Performance of artificial neural network and regression techniques for rainfall-runoff prediction. / El-Shafie, A.; Mukhlisin, M.; Najah, Ali A.; Taha, Mohd. Raihan.

In: International Journal of Physical Sciences, Vol. 6, No. 8, 04.2011, p. 1997-2003.

Research output: Contribution to journalArticle

@article{5d8143359b324a91b6d3d36835b502c4,
title = "Performance of artificial neural network and regression techniques for rainfall-runoff prediction",
abstract = "Different types of methods have been used in runoff prediction involving conceptual and empirical models. Nevertheless, none of these methods can be considered as a single superior model. Owing to the complexity of the hydrological process, the accurate runoff is difficult to be predicted using the linear recurrence relations or physically based watershed. The linear recurrence relation model does not attempt to take into account the nonlinear dynamic of the hydrological process. The Artificial Neural Network (ANN) is a new technique with a flexible mathematical structure that is capable of identifying complex non-linear relationships between input and output data when compared to other classical modelling techniques. Therefore, the present study aims to utilize an Artificial Neural Network (ANN) to predict the rainfall-runoff relationship in a catchment area located in a Tanakami region of Japan. The study illustrates the applications of the feed forward back propagation with hyperbolic tangent neurons in the hidden layer and linear neuron in the output layer is used for rainfall prediction. To evaluate the performance of the proposed model, three statistical indexes were used, namely; Correlation coefficient (R), mean square error (MSE) and correlation of determination (R2). The results showed that the feed forward back propagation Neural Network (ANN) can describe the behaviour of rainfall-runoff relation more accurately than the classical regression model.",
keywords = "Artificial neural network, Linear regression, Rainfall-runoff",
author = "A. El-Shafie and M. Mukhlisin and Najah, {Ali A.} and Taha, {Mohd. Raihan}",
year = "2011",
month = "4",
language = "English",
volume = "6",
pages = "1997--2003",
journal = "International Journal of Physical Sciences",
issn = "1992-1950",
publisher = "Academic Journals",
number = "8",

}

TY - JOUR

T1 - Performance of artificial neural network and regression techniques for rainfall-runoff prediction

AU - El-Shafie, A.

AU - Mukhlisin, M.

AU - Najah, Ali A.

AU - Taha, Mohd. Raihan

PY - 2011/4

Y1 - 2011/4

N2 - Different types of methods have been used in runoff prediction involving conceptual and empirical models. Nevertheless, none of these methods can be considered as a single superior model. Owing to the complexity of the hydrological process, the accurate runoff is difficult to be predicted using the linear recurrence relations or physically based watershed. The linear recurrence relation model does not attempt to take into account the nonlinear dynamic of the hydrological process. The Artificial Neural Network (ANN) is a new technique with a flexible mathematical structure that is capable of identifying complex non-linear relationships between input and output data when compared to other classical modelling techniques. Therefore, the present study aims to utilize an Artificial Neural Network (ANN) to predict the rainfall-runoff relationship in a catchment area located in a Tanakami region of Japan. The study illustrates the applications of the feed forward back propagation with hyperbolic tangent neurons in the hidden layer and linear neuron in the output layer is used for rainfall prediction. To evaluate the performance of the proposed model, three statistical indexes were used, namely; Correlation coefficient (R), mean square error (MSE) and correlation of determination (R2). The results showed that the feed forward back propagation Neural Network (ANN) can describe the behaviour of rainfall-runoff relation more accurately than the classical regression model.

AB - Different types of methods have been used in runoff prediction involving conceptual and empirical models. Nevertheless, none of these methods can be considered as a single superior model. Owing to the complexity of the hydrological process, the accurate runoff is difficult to be predicted using the linear recurrence relations or physically based watershed. The linear recurrence relation model does not attempt to take into account the nonlinear dynamic of the hydrological process. The Artificial Neural Network (ANN) is a new technique with a flexible mathematical structure that is capable of identifying complex non-linear relationships between input and output data when compared to other classical modelling techniques. Therefore, the present study aims to utilize an Artificial Neural Network (ANN) to predict the rainfall-runoff relationship in a catchment area located in a Tanakami region of Japan. The study illustrates the applications of the feed forward back propagation with hyperbolic tangent neurons in the hidden layer and linear neuron in the output layer is used for rainfall prediction. To evaluate the performance of the proposed model, three statistical indexes were used, namely; Correlation coefficient (R), mean square error (MSE) and correlation of determination (R2). The results showed that the feed forward back propagation Neural Network (ANN) can describe the behaviour of rainfall-runoff relation more accurately than the classical regression model.

KW - Artificial neural network

KW - Linear regression

KW - Rainfall-runoff

UR - http://www.scopus.com/inward/record.url?scp=79958705260&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958705260&partnerID=8YFLogxK

M3 - Article

VL - 6

SP - 1997

EP - 2003

JO - International Journal of Physical Sciences

JF - International Journal of Physical Sciences

SN - 1992-1950

IS - 8

ER -